CN113590901A - Material recommendation method, device and equipment based on user grouping and storage medium - Google Patents
Material recommendation method, device and equipment based on user grouping and storage medium Download PDFInfo
- Publication number
- CN113590901A CN113590901A CN202110872837.5A CN202110872837A CN113590901A CN 113590901 A CN113590901 A CN 113590901A CN 202110872837 A CN202110872837 A CN 202110872837A CN 113590901 A CN113590901 A CN 113590901A
- Authority
- CN
- China
- Prior art keywords
- user
- users
- user group
- information
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000463 material Substances 0.000 title claims abstract description 178
- 238000000034 method Methods 0.000 title claims abstract description 63
- 239000013598 vector Substances 0.000 claims description 46
- 238000001914 filtration Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 10
- 238000000638 solvent extraction Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, can be applied to smart cities, and discloses a material recommendation method based on user grouping, which comprises the following steps: clustering and dividing the users according to the dimension portrait information of the users to obtain a plurality of user groups; aiming at each user group, determining a material recommendation list of the user group according to material information recently clicked and browsed by each user in the user group; and recommending the material information in the corresponding material recommendation list for the users in the user group according to a preset strategy. The users are divided in a group mode, so that the interests of the users in the group are similar, and the interests of the users in the group are different, thereby facilitating better management and cultivation of user relationships. The method comprises the steps of determining a material recommendation list of a user group according to materials clicked and browsed by each user in the user group so as to recommend the materials in the group unit, achieving that the users in the group obtain interesting materials, and avoiding the problems of difficult user management and narrower recommended materials for the users due to thousands of personalized recommendation modes.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a material recommendation method, a material recommendation device, material recommendation equipment and a storage medium based on user grouping.
Background
The intelligent recommendation technology is applied to various aspects of life, for example, a user receives recommendation of related commodities when browsing commodities on an e-commerce platform, and receives interested video recommendation when browsing a video website. The intelligent recommendation technology at the present stage realizes the individuation based on thousands of people and thousands of faces of users.
However, at present, an individual recommendation mode based on thousands of users is only to intelligently recommend a single user, so that recommended materials (news, commodities, videos, pictures and the like) are difficult to distribute to a specified user group in a group mode, the management complexity of a target user is increased, the material owner is prevented from further reaching the activities of the user, and the problem that material information recommended to the target user is not comprehensive enough is caused.
Disclosure of Invention
The present invention provides a method, an apparatus, a device and a storage medium for recommending materials based on user grouping, which are provided to overcome the above-mentioned disadvantages of the prior art.
The invention provides a material recommendation method based on user grouping in a first aspect, which comprises the following steps:
clustering and dividing the users according to the dimension portrait information of each user to obtain a plurality of user groups;
aiming at each user group, determining a material recommendation list of the user group according to material information recently clicked and browsed by each user in the user group;
and recommending the material information in the material recommendation list of the user group for the users in the user group according to a preset strategy.
In some embodiments of the present application, the clustering and dividing users according to the dimension profile information of each user to obtain a plurality of user groups includes:
acquiring dimension portrait information of each user; for each user, searching a word vector corresponding to each dimension portrait information of the user based on a preset word vector library, and determining comprehensive vector information of the user according to the word vector corresponding to each dimension portrait information of the user; and clustering and dividing the users based on the comprehensive vector information of each user to obtain a plurality of user groups.
In some embodiments of the present application, the clustering and partitioning users based on the comprehensive vector information of each user to obtain a plurality of user groups includes:
inputting the comprehensive vector information of each user into a preset clustering algorithm, clustering and dividing the users by the clustering algorithm based on the comprehensive vector information of each user, and outputting a plurality of initial user groups, wherein each initial user group comprises a clustering center point and users clustered into one class; and filtering the initial user group and the users in the initial user group according to the distance between the clustering center point in the initial user group and the users clustered into one class, and taking the filtered initial user group as a final user group.
In some embodiments of the present application, the filtering the initial user group and the users in the initial user group according to the distance between the clustering center point in the initial user group and the users clustered as a class includes:
calculating the sum of the distances between each user in the initial user group and the clustering center point aiming at each initial user group; filtering the initial user group if the distance sum is greater than a first threshold; and aiming at each remaining initial user group, calculating the distance between each user in the initial user group and the clustering center point, and filtering the users with the distance larger than a second threshold value from the initial user group.
In some embodiments of the present application, the determining a material recommendation list of the user group according to material information recently clicked and browsed by each user in the user group includes:
acquiring preset quantity of material information recently clicked and browsed by each user in the user group; counting the co-occurrence times of each material information; and sequencing the material information according to the sequence of the co-occurrence times from high to low, and acquiring N pieces of material information which are sequenced at the top from the sequencing result to be used as a material recommendation list of the user group.
In some embodiments of the present application, recommending, according to a preset policy, material information in a material recommendation list of a user group for a user in the user group includes:
receiving a browsing request of users in the user group; filtering the material information recommended to the user in the material recommendation list of the user group, and recommending the residual material information to the user; or inputting all material information in the material recommendation list into a preset sorting model, so that the sorting model carries out recommendation scoring on each material information, and recommending the material information with the recommendation score higher than a preset score to the user; or, according to rules that the adjacent material information belongs to different categories, rearranging the material information in the material recommendation list, and recommending the rearranged material information to the user.
A second aspect of the present invention provides a material recommendation device based on user grouping, where the device includes:
the clustering module is used for clustering and dividing the users according to the dimension portrait information of each user to obtain a plurality of user groups;
the material determining module is used for determining a material recommending list of each user group according to material information recently clicked and browsed by each user in the user groups aiming at each user group;
and the material recommending module is used for recommending the material information in the material recommending list of the user group for the users in the user group according to a preset strategy.
A third aspect of the present invention proposes an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method according to the first aspect when executing the program.
A fourth aspect of the present invention proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method according to the first aspect as described above.
Based on the above first aspect and second aspect, the method and apparatus for recommending materials based on user grouping according to the present invention at least have the following advantages:
the users are divided in a group mode, so that the interests of the users in the group are similar, and the interests of the users in the group are different, thereby facilitating better management and cultivation of user relationships. The method and the device for recommending the materials in the user group determine the material recommendation list of the user group according to the materials clicked and browsed by each user in the user group so as to recommend the materials in the group unit, achieve that the users in the group obtain the interesting materials, simultaneously avoid the problems that the user management is difficult and the material information recommended to the users is not comprehensive due to thousands of personalized recommendation modes, and meanwhile, can also explore the interests of the users in the group, help the users to find out the blind areas of interest, and improve the user dependence.
The method can be applied to the technical field of smart cities, so that the construction of the smart cities is promoted.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart illustrating an embodiment of a method for user-grouping-based material recommendation according to an exemplary embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating user cluster partitioning according to the embodiment shown in FIG. 1;
FIG. 3 is a schematic structural diagram illustrating a user-grouping-based material recommendation apparatus according to an exemplary embodiment of the present invention;
FIG. 4 is a diagram illustrating a hardware configuration of an electronic device according to an exemplary embodiment of the present invention;
fig. 5 is a schematic diagram illustrating a structure of a storage medium according to an exemplary embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The intelligent recommendation technology is applied to various aspects of life, for example, a user can receive recommendation of related commodities when browsing the commodities on an e-commerce platform, and the user can receive interested video recommendation when shopping a video website. The current recommendation technology realizes the personalization based on thousands of people and thousands of faces of users. Google, amazon, aribaba, FaceBook, etc. companies also recommend corresponding materials (e.g., news, merchandise, videos, pictures, etc.) based on this type of technology.
However, the above recommendation techniques for thousands of people neglect the group characteristics of users, which causes the difficulty in distributing materials to a designated user group in a group manner in the material recommendation method at the present stage, increases the management complexity of the target user, prevents the material owner from further reaching the activities of the users, and causes the problem that the recommended material information recommended to the users is not comprehensive enough.
In order to solve the technical problems, the invention provides a material recommendation method based on user grouping, namely, clustering and dividing users according to dimension portrait information of the users to obtain a plurality of user groups, then determining a material recommendation list of each user group according to material information recently clicked and browsed by each user in the user group aiming at each user group, and then recommending the material information in the corresponding material recommendation list for the users in the user groups according to a preset strategy.
Based on the above description, the users are divided into groups, so that the interests of the users in the groups are similar, and the interests of the users in the groups are different, thereby facilitating better management and cultivation of user relationships. The method and the device for recommending the materials in the user group determine the material recommendation list of the user group according to the materials clicked and browsed by each user in the user group so as to recommend the materials in the group unit, achieve that the users in the group obtain the interesting materials, simultaneously avoid the problems that the user management is difficult and the material information recommended to the users is not comprehensive due to thousands of personalized recommendation modes, and meanwhile, can also explore the interests of the users in the group, help the users to find out the blind areas of interest, and improve the user dependence.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
The first embodiment is as follows:
fig. 1 is a flowchart of an embodiment of a material recommendation method based on user grouping according to an exemplary embodiment of the present invention, where the material recommendation method based on user grouping may be applied to a computer device, and the computer device may be a terminal device, a mobile terminal, a PC, a server, and the like, as shown in fig. 1, the recommendation method includes the following steps:
step 101: and clustering and dividing the users according to the dimension portrait information of each user to obtain a plurality of user groups.
The dimension portrait information of the user refers to label information describing the user from various aspects, and the portrait information generally includes two major types of information, namely a base portrait and an interest portrait. For example, the base representation includes an age dimension, a gender dimension, a height dimension, etc., and for the interest representation includes an interest category dimension, an interest word dimension, an interest subject dimension, etc.
It should be noted that after clustering and partitioning users to obtain a plurality of user groups, the users in the groups have close similarity, and the users between the groups have significant difference.
For a specific implementation of the process of step 101, reference may be made to the following detailed description of embodiments, and the present invention will not be described in detail herein.
Step 102: and aiming at each user group, determining a material recommendation list of the user group according to the material information recently clicked and browsed by each user in the user group.
The material information generally refers to a recommended entity, and may be, for example, news, commodities, videos, pictures, and the like.
In an optional specific implementation manner, a preset number of pieces of material information recently clicked and browsed by each user in a user group is obtained, then the co-occurrence times of the material information are counted, the material information is sorted according to the sequence of the co-occurrence times from high to low, and N pieces of material information which are sorted at the top are obtained from a sorting result and used as a material recommendation list of the user group.
Because the interests of the users in the group have close similarity, the users in the group can inevitably click and browse the same material information, the counted co-occurrence times of the material information represent the interest degree of the users in the group on the same material information, and the material information with higher interest degree (namely the material information with higher co-occurrence times) is added into the material recommendation list, so that the users in the group can be better recommended with the interested materials.
For example, suppose that there are 100 users in a certain user group, 5 pieces of material information that each user has clicked and browsed recently are acquired, and then in a set of 100 × 5 — 500 pieces of material information, the co-occurrence times of each piece of material information, that is, the times of occurrence of each piece of material information in the set are counted, then the pieces of material information are sorted in the order of the co-occurrence times from high to low, and the top N pieces of material information are taken from the sorted results as recommendation results of the users in the group.
It should be noted that after the material recommendation list of the user group is determined, the material recommendation list corresponding to the user group may be stored in the cache database, so that when a request is made by a user in the group, the material information in the material recommendation list is recommended to the user.
Step 103: and recommending the material information in the material recommendation list of the user group for the users in the user group according to a preset strategy.
In an optional specific embodiment, when a browsing request of a user in the user group is received, the material recommendation list corresponding to the user group is searched from the cache database, the material information recommended to the user in the material recommendation list can be filtered, and the remaining material information is recommended to the user.
In another optional specific embodiment, when the material recommendation list is found, all the material information in the material recommendation list may be input into a preset sorting model, so that each material information is recommended and scored by the sorting model, and the material information with the recommendation score higher than the preset score is recommended to the user.
In another optional specific embodiment, when the material recommendation list is found, the material information in the material recommendation list may be rearranged according to rules that the adjacent material information belongs to different categories, and the rearranged material information is recommended to the user.
It will be appreciated by those skilled in the art that two or more of the various strategies described above may also be combined for recommendation.
By this, the flow shown in fig. 1 is completed, and the users are divided into groups, so that the interests of the users in the groups are similar, and the interests of the users in the groups are different, thereby facilitating better management and cultivation of user relationships. The method and the device for recommending the materials in the user group determine the material recommendation list of the user group according to the materials clicked and browsed by each user in the user group so as to recommend the materials in the group unit, achieve that the users in the group obtain the interesting materials, simultaneously avoid the problems that the user management is difficult and the material information recommended to the users is not comprehensive due to thousands of personalized recommendation modes, and meanwhile, can also explore the interests of the users in the group, help the users to find out the blind areas of interest, and improve the user dependence.
The method can be applied to the technical field of smart cities, so that the construction of the smart cities is promoted.
Example two:
fig. 2 is a schematic flow chart of user cluster partitioning according to an exemplary embodiment of the present invention, based on the embodiment shown in fig. 1, in step 101, the process for user cluster partitioning includes the following steps:
step 201: and acquiring dimension portrait information of each user.
The dimension portrait information of the user refers to label information describing the user from various aspects, and the portrait information generally includes two major types of information, namely a base portrait and an interest portrait. For example, the base representation includes an age dimension, a gender dimension, a height dimension, etc., and for the interest representation includes an interest category dimension, an interest word dimension, an interest subject dimension, etc.
Step 202: for each user, searching a word vector corresponding to each dimension portrait information of the user based on a preset word vector library, and determining comprehensive vector information of the user according to the word vector corresponding to each dimension portrait information of the user.
The word vector library can be obtained by pre-training, word vectors of different words are recorded in the library, and the length of the word vector of each word is the same.
For example, a gender word is recorded in the word vector library: a male word vector and a female word vector; interest category words: word vectors for sports, word vectors for entertainment, word vectors for finance, and the like.
In an optional specific embodiment, in the process of determining the comprehensive vector information of the user according to the word vectors corresponding to the dimensional portrait information of the user, the weighted sum of the word vectors corresponding to the dimensional portrait information of the user may be counted, and an average value of the weighted sum is used as the comprehensive vector information of the user.
The weights adopted by the weighted summation of the word vectors of the image information of each dimension can be set in advance according to actual requirements.
For example, the image information that requires much attention may be weighted more heavily, and the image information that is less important may be weighted less heavily. The sum of the weights of the dimensional image information is only required to be 1.
It should be noted that the vector lengths of the integrated vector information of the users are all kept consistent, so as to facilitate the cluster partitioning calculation.
In a specific implementation, some dimension image information may have multiple tag values, for example, in the dimension of interest subject, N tags of interest are provided, each tag value corresponds to one word vector, in order to ensure that the word vectors of each dimension image information have the same length, and facilitate subsequent statistics of integrated vector information, multiple word vectors of image information including multiple tags may be subjected to weighted summation, and the summation result is used as the word vector of the dimension image information.
When the weighted sum is performed, the weight of each label is used for representing the interest degree of the user, and the corresponding weight can be obtained by calculating according to the click times, sharing times and comment times of the user on the material belonging to the label.
In another implementation, the word vectors of a certain number of labels in the image information including a plurality of labels, which are ranked in the top order, may be subjected to weighted summation, and the summation result may be used as the word vector of the image information of this dimension.
Step 203: and clustering and dividing the users based on the comprehensive vector information of each user to obtain a plurality of user groups.
In an optional implementation manner, the comprehensive vector information of each user may be input into a preset clustering algorithm, the clustering algorithm performs clustering division on the users based on the comprehensive vector information of each user, and outputs a plurality of initial user groups, each initial user group includes a clustering center point and users clustered into one class, and then the users in the initial user groups and the users in the initial user groups are filtered according to a distance between the clustering center point in the initial user groups and the users clustered into one class, and the filtered initial user groups are used as final user groups.
After the clustering division is carried out on the users through the clustering algorithm, the users in the clusters have close similarity, the users between the clusters have obvious difference, the initial user clusters and the users in the clusters obtained through the clustering division are filtered through a filtering technical means, the clustering result can be optimized, the confidence coefficient of the clustering result is ensured, and the clustering effect is optimal.
It can be understood by those skilled in the art that the clustering algorithm may be an artificial intelligence unsupervised clustering algorithm, or an artificial intelligence supervised clustering algorithm, which is not specifically limited in the present invention.
In some optional embodiments, for a process of filtering the initial user group and the users in the initial user group according to the distance between the clustering center point in the initial user group and the users clustered into one class, for each initial user group, a sum of distances between each user in the initial user group and the clustering center point may be calculated, and if the sum of distances is greater than a first threshold, the initial user group is filtered; and then, aiming at each remaining initial user group, calculating the distance between each user in the initial user group and the cluster center point, and filtering the users with the distance larger than a second threshold value from the initial user group.
That is, the initial user group is integrally filtered according to the distance between the users in the initial user group and the clustering center point, and then the users in the remaining initial user groups are filtered, so that the final initial user group after filtering achieves the best clustering effect.
The distance sum between the users in the cluster and the cluster center point represents the overall clustering degree of the user cluster, and the smaller the distance sum, the higher the polymerization degree; the distance between the users in the cluster and the cluster center point represents the clustering degree of a single user, and the smaller the distance is, the higher the clustering degree is.
At this point, the user cluster division process shown in fig. 2 is completed.
Corresponding to the embodiment of the material recommending method based on user grouping, the invention also provides an embodiment of a material recommending device based on user grouping.
Fig. 3 is a schematic structural diagram of a material recommendation device based on user grouping according to an exemplary embodiment of the present invention, the device is configured to execute the material recommendation method based on user grouping according to any of the embodiments described above, and as shown in fig. 3, the material recommendation device based on user grouping includes:
the clustering module 310 is configured to perform clustering division on the users according to the dimension portrait information of each user to obtain a plurality of user groups;
the material determining module 320 is configured to determine, for each user group, a material recommendation list of the user group according to material information recently clicked and browsed by each user in the user group;
and the material recommending module 330 is configured to recommend material information in the material recommending list of the user group for the users in the user group according to a preset strategy.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the invention. One of ordinary skill in the art can understand and implement it without inventive effort.
The embodiment of the invention also provides electronic equipment corresponding to the material recommendation method based on user grouping provided by the embodiment, so as to execute the material recommendation method based on user grouping.
Fig. 4 is a hardware block diagram of an electronic device according to an exemplary embodiment of the present invention, the electronic device including: a communication interface 601, a processor 602, a memory 603, and a bus 604; the communication interface 601, the processor 602 and the memory 603 communicate with each other via a bus 604. The processor 602 may execute the above-described user-clustering-based material recommendation method by reading and executing machine executable instructions in the memory 603 corresponding to the control logic of the user-clustering-based material recommendation method, and the specific content of the method is described in the above embodiments, which will not be described herein again.
The memory 603 referred to in this disclosure may be any electronic, magnetic, optical, or other physical storage device that can contain stored information, such as executable instructions, data, and so forth. Specifically, the Memory 603 may be a RAM (Random Access Memory), a flash Memory, a storage drive (e.g., a hard disk drive), any type of storage disk (e.g., an optical disk, a DVD, etc.), or similar storage medium, or a combination thereof. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 601 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The processor 602 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 602. The Processor 602 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.
The electronic device provided by the embodiment of the application and the material recommending method based on user grouping provided by the embodiment of the application have the same inventive concept and have the same beneficial effects as the method adopted, operated or realized by the electronic device.
Referring to fig. 5, the computer readable storage medium is an optical disc 30, and a computer program (i.e., a program product) is stored thereon, and when being executed by a processor, the computer program may execute the material recommendation method based on user grouping provided by any of the foregoing embodiments.
It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory, or other optical and magnetic storage media, which are not described in detail herein.
The computer-readable storage medium provided by the above embodiment of the present application and the material recommendation method based on user grouping provided by the embodiment of the present application have the same inventive concept and have the same beneficial effects as the method adopted, operated or implemented by the application program stored in the computer-readable storage medium.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A material recommendation method based on user grouping is characterized by comprising the following steps:
clustering and dividing the users according to the dimension portrait information of each user to obtain a plurality of user groups;
aiming at each user group, determining a material recommendation list of the user group according to material information recently clicked and browsed by each user in the user group;
and recommending the material information in the material recommendation list of the user group for the users in the user group according to a preset strategy.
2. The method of claim 1, wherein clustering users according to dimension profile information of each user to obtain a plurality of user groups comprises:
acquiring dimension portrait information of each user;
for each user, searching a word vector corresponding to each dimension portrait information of the user based on a preset word vector library, and determining comprehensive vector information of the user according to the word vector corresponding to each dimension portrait information of the user;
and clustering and dividing the users based on the comprehensive vector information of each user to obtain a plurality of user groups.
3. The method of claim 2, wherein the clustering the users based on the comprehensive vector information of each user to obtain a plurality of user groups comprises:
inputting the comprehensive vector information of each user into a preset clustering algorithm, clustering and dividing the users by the clustering algorithm based on the comprehensive vector information of each user, and outputting a plurality of initial user groups, wherein each initial user group comprises a clustering center point and users clustered into one class;
and filtering the initial user group and the users in the initial user group according to the distance between the clustering center point in the initial user group and the users clustered into one class, and taking the filtered initial user group as a final user group.
4. The method of claim 3, wherein the filtering the initial user group and the users in the initial user group according to the distance between the clustering center point in the initial user group and the users clustered as a cluster comprises:
calculating the sum of the distances between each user in the initial user group and the clustering center point aiming at each initial user group;
filtering the initial user group if the distance sum is greater than a first threshold;
and aiming at each remaining initial user group, calculating the distance between each user in the initial user group and the clustering center point, and filtering the users with the distance larger than a second threshold value from the initial user group.
5. The method according to claim 1, wherein the determining the material recommendation list of the user group according to the material information recently clicked and browsed by each user in the user group comprises:
acquiring preset quantity of material information recently clicked and browsed by each user in the user group;
counting the co-occurrence times of each material information;
and sequencing the material information according to the sequence of the co-occurrence times from high to low, and acquiring N pieces of material information which are sequenced at the top from the sequencing result to be used as a material recommendation list of the user group.
6. The method according to claim 1, wherein the recommending the material information in the material recommendation list of the user group for the users in the user group according to the preset strategy comprises:
receiving a browsing request of users in the user group;
filtering the material information recommended to the user in the material recommendation list of the user group, and recommending the residual material information to the user; alternatively, the first and second electrodes may be,
inputting all material information in the material recommendation list into a preset sorting model, so that the sorting model carries out recommendation scoring on each material information, and recommending the material information with the recommendation score higher than a preset score to the user; alternatively, the first and second electrodes may be,
and rearranging the material information in the material recommendation list according to different rules of the categories of the adjacent material information, and recommending the rearranged material information to the user.
7. The method of claim 6, further comprising:
and after receiving a browsing request of a user in the user group, recommending the material information in the material recommendation list of the user group to the user.
8. A material recommendation device based on user grouping, the device comprising:
the clustering module is used for clustering and dividing the users according to the dimension portrait information of each user to obtain a plurality of user groups;
the material determining module is used for determining a material recommending list of each user group according to material information recently clicked and browsed by each user in the user groups aiming at each user group;
and the material recommending module is used for recommending the material information in the material recommending list of the user group for the users in the user group according to a preset strategy.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1-7 are implemented when the processor executes the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110872837.5A CN113590901A (en) | 2021-07-30 | 2021-07-30 | Material recommendation method, device and equipment based on user grouping and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110872837.5A CN113590901A (en) | 2021-07-30 | 2021-07-30 | Material recommendation method, device and equipment based on user grouping and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113590901A true CN113590901A (en) | 2021-11-02 |
Family
ID=78252782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110872837.5A Pending CN113590901A (en) | 2021-07-30 | 2021-07-30 | Material recommendation method, device and equipment based on user grouping and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113590901A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314573A (en) * | 2023-09-27 | 2023-12-29 | 深圳市斯堡霖科技有限公司 | Network marketing system based on user matching |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111552883A (en) * | 2020-05-13 | 2020-08-18 | 咪咕文化科技有限公司 | Content recommendation method and computer-readable storage medium |
-
2021
- 2021-07-30 CN CN202110872837.5A patent/CN113590901A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111552883A (en) * | 2020-05-13 | 2020-08-18 | 咪咕文化科技有限公司 | Content recommendation method and computer-readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314573A (en) * | 2023-09-27 | 2023-12-29 | 深圳市斯堡霖科技有限公司 | Network marketing system based on user matching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11216496B2 (en) | Visual interactive search | |
| CN109359244B (en) | Personalized information recommendation method and device | |
| CN108121737B (en) | Method, device and system for generating business object attribute identifier | |
| CN105224699B (en) | News recommendation method and device | |
| WO2018041168A1 (en) | Information pushing method, storage medium and server | |
| CN111898031B (en) | Method and device for obtaining user portrait | |
| US20120185481A1 (en) | Method and Apparatus for Executing a Recommendation | |
| CN109636494A (en) | Drug recommended method and system | |
| CN111310038B (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN109460519B (en) | Browsing object recommendation method and device, storage medium and server | |
| CN112052387B (en) | Content recommendation method, device and computer readable storage medium | |
| CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
| CN110008376A (en) | User's portrait vector generation method and device | |
| Liu et al. | Fast recommendation on latent collaborative relations | |
| CN112163149A (en) | Method and device for recommending messages | |
| CN113590901A (en) | Material recommendation method, device and equipment based on user grouping and storage medium | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN110321490B (en) | Recommendation method, device, equipment and computer readable storage medium | |
| CN110020918B (en) | Recommendation information generation method and system | |
| CN115730217A (en) | Model training method, material recalling method and device | |
| CN114330519A (en) | Data determination method and device, electronic equipment and storage medium | |
| CN114461822A (en) | Resource processing method, device, equipment and storage medium | |
| CN113744021A (en) | Recommendation method, recommendation device, computer storage medium and recommendation system | |
| CN113393303A (en) | Article recommendation method, device, equipment and storage medium | |
| CN117786234B (en) | Multimode resource recommendation method based on two-stage comparison learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |